diff --git a/llvm/lib/CodeGen/InterleavedAccessPass.cpp b/llvm/lib/CodeGen/InterleavedAccessPass.cpp
index 960c795..49f1504 100644
--- a/llvm/lib/CodeGen/InterleavedAccessPass.cpp
+++ b/llvm/lib/CodeGen/InterleavedAccessPass.cpp
@@ -571,6 +571,36 @@
   return true;
 }
 
+static bool isInterleaveIntrinsic(Intrinsic::ID IID) {
+  switch (IID) {
+  case Intrinsic::vector_interleave2:
+  case Intrinsic::vector_interleave3:
+  case Intrinsic::vector_interleave4:
+  case Intrinsic::vector_interleave5:
+  case Intrinsic::vector_interleave6:
+  case Intrinsic::vector_interleave7:
+  case Intrinsic::vector_interleave8:
+    return true;
+  default:
+    return false;
+  }
+}
+
+static bool isDeinterleaveIntrinsic(Intrinsic::ID IID) {
+  switch (IID) {
+  case Intrinsic::vector_deinterleave2:
+  case Intrinsic::vector_deinterleave3:
+  case Intrinsic::vector_deinterleave4:
+  case Intrinsic::vector_deinterleave5:
+  case Intrinsic::vector_deinterleave6:
+  case Intrinsic::vector_deinterleave7:
+  case Intrinsic::vector_deinterleave8:
+    return true;
+  default:
+    return false;
+  }
+}
+
 static unsigned getIntrinsicFactor(const IntrinsicInst *II) {
   switch (II->getIntrinsicID()) {
   case Intrinsic::vector_deinterleave2:
@@ -579,12 +609,21 @@
   case Intrinsic::vector_deinterleave3:
   case Intrinsic::vector_interleave3:
     return 3;
+  case Intrinsic::vector_deinterleave4:
+  case Intrinsic::vector_interleave4:
+    return 4;
   case Intrinsic::vector_deinterleave5:
   case Intrinsic::vector_interleave5:
     return 5;
+  case Intrinsic::vector_deinterleave6:
+  case Intrinsic::vector_interleave6:
+    return 6;
   case Intrinsic::vector_deinterleave7:
   case Intrinsic::vector_interleave7:
     return 7;
+  case Intrinsic::vector_deinterleave8:
+  case Intrinsic::vector_interleave8:
+    return 8;
   default:
     llvm_unreachable("Unexpected intrinsic");
   }
@@ -605,10 +644,9 @@
 //  to reorder them by interleaving these values.
 static void interleaveLeafValues(MutableArrayRef<Value *> SubLeaves) {
   unsigned NumLeaves = SubLeaves.size();
-  if (NumLeaves == 2 || !isPowerOf2_64(NumLeaves))
-    return;
-
   assert(isPowerOf2_32(NumLeaves) && NumLeaves > 1);
+  if (NumLeaves == 2)
+    return;
 
   const unsigned HalfLeaves = NumLeaves / 2;
   // Visit the sub-trees.
@@ -627,10 +665,7 @@
 static bool
 getVectorInterleaveFactor(IntrinsicInst *II, SmallVectorImpl<Value *> &Operands,
                           SmallVectorImpl<Instruction *> &DeadInsts) {
-  assert(II->getIntrinsicID() == Intrinsic::vector_interleave2 ||
-         II->getIntrinsicID() == Intrinsic::vector_interleave3 ||
-         II->getIntrinsicID() == Intrinsic::vector_interleave5 ||
-         II->getIntrinsicID() == Intrinsic::vector_interleave7);
+  assert(isInterleaveIntrinsic(II->getIntrinsicID()));
 
   // Visit with BFS
   SmallVector<IntrinsicInst *, 8> Queue;
@@ -660,13 +695,17 @@
   }
 
   const unsigned Factor = Operands.size();
-  // Currently we only recognize factors of 3, 5, 7, and powers of 2.
+  // Currently we only recognize factors 2...8 and other powers of 2.
   // FIXME: should we assert here instead?
   if (Factor <= 1 ||
       (!isPowerOf2_32(Factor) && Factor != getIntrinsicFactor(II)))
     return false;
 
-  interleaveLeafValues(Operands);
+  // Recursively interleaved factors need to have their values reordered
+  // TODO: Remove once the loop vectorizer no longer recursively interleaves
+  // factors 4 + 8
+  if (isPowerOf2_32(Factor) && getIntrinsicFactor(II) == 2)
+    interleaveLeafValues(Operands);
   return true;
 }
 
@@ -674,10 +713,7 @@
 getVectorDeinterleaveFactor(IntrinsicInst *II,
                             SmallVectorImpl<Value *> &Results,
                             SmallVectorImpl<Instruction *> &DeadInsts) {
-  assert(II->getIntrinsicID() == Intrinsic::vector_deinterleave2 ||
-         II->getIntrinsicID() == Intrinsic::vector_deinterleave3 ||
-         II->getIntrinsicID() == Intrinsic::vector_deinterleave5 ||
-         II->getIntrinsicID() == Intrinsic::vector_deinterleave7);
+  assert(isDeinterleaveIntrinsic(II->getIntrinsicID()));
   using namespace PatternMatch;
   if (!II->hasNUses(getIntrinsicFactor(II)))
     return false;
@@ -737,13 +773,17 @@
   }
 
   const unsigned Factor = Results.size();
-  // Currently we only recognize factors of 3, 5, 7, and powers of 2.
+  // Currently we only recognize factors of 2...8 and other powers of 2.
   // FIXME: should we assert here instead?
   if (Factor <= 1 ||
       (!isPowerOf2_32(Factor) && Factor != getIntrinsicFactor(II)))
     return 0;
 
-  interleaveLeafValues(Results);
+  // Recursively interleaved factors need to have their values reordered
+  // TODO: Remove once the loop vectorizer no longer recursively interleaves
+  // factors 4 + 8
+  if (isPowerOf2_32(Factor) && getIntrinsicFactor(II) == 2)
+    interleaveLeafValues(Results);
   return true;
 }
 
@@ -902,24 +942,10 @@
       Changed |= lowerInterleavedStore(&I, DeadInsts);
 
     if (auto *II = dyn_cast<IntrinsicInst>(&I)) {
-      // At present, we only have intrinsics to represent (de)interleaving
-      // with a factor of 2,3,5 and 7.
-      switch (II->getIntrinsicID()) {
-      case Intrinsic::vector_deinterleave2:
-      case Intrinsic::vector_deinterleave3:
-      case Intrinsic::vector_deinterleave5:
-      case Intrinsic::vector_deinterleave7:
+      if (isDeinterleaveIntrinsic(II->getIntrinsicID()))
         Changed |= lowerDeinterleaveIntrinsic(II, DeadInsts);
-        break;
-      case Intrinsic::vector_interleave2:
-      case Intrinsic::vector_interleave3:
-      case Intrinsic::vector_interleave5:
-      case Intrinsic::vector_interleave7:
+      else if (isInterleaveIntrinsic(II->getIntrinsicID()))
         Changed |= lowerInterleaveIntrinsic(II, DeadInsts);
-        break;
-      default:
-        break;
-      }
     }
   }
 
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-deinterleave-load.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-deinterleave-load.ll
index 31529b1..c2ae1ce 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-deinterleave-load.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-deinterleave-load.ll
@@ -281,6 +281,26 @@
 ; CHECK-NEXT:    vlseg4e8.v v8, (a0)
 ; CHECK-NEXT:    ret
   %vec = load <32 x i8>, ptr %p
+  %d0 = call { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @llvm.vector.deinterleave4(<32 x i8> %vec)
+  %t0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 0
+  %t1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 1
+  %t2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 2
+  %t3 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 3
+  %res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
+  %res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 1
+  %res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
+  %res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
+  ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3
+}
+
+; TODO: Remove once recursive deinterleaving support is removed
+define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor4_recursive(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_factor4_recursive:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT:    vlseg4e8.v v8, (a0)
+; CHECK-NEXT:    ret
+  %vec = load <32 x i8>, ptr %p
   %d0 = call {<16 x i8>, <16 x i8>} @llvm.vector.deinterleave2.v32i8(<32 x i8> %vec)
   %d0.0 = extractvalue { <16 x i8>, <16 x i8> } %d0, 0
   %d0.1 = extractvalue { <16 x i8>, <16 x i8> } %d0, 1
@@ -319,6 +339,29 @@
   ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res4
 }
 
+define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor6(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_factor6:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT:    vlseg6e8.v v8, (a0)
+; CHECK-NEXT:    ret
+  %vec = load <48 x i8>, ptr %p
+  %d0 = call { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @llvm.vector.deinterleave6(<48 x i8> %vec)
+  %t0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 0
+  %t1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 1
+  %t2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 2
+  %t3 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 3
+  %t4 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 4
+  %t5 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 5
+  %res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
+  %res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 1
+  %res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
+  %res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
+  %res4 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t4, 4
+  %res5 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res4, <8 x i8> %t5, 5
+  ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res5
+}
+
 define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor7(ptr %p) {
 ; CHECK-LABEL: vector_deinterleave_load_factor7:
 ; CHECK:       # %bb.0:
@@ -339,14 +382,43 @@
   %res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
   %res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
   %res4 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t4, 4
-  %res5 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t5, 5
-  %res6 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t6, 6
+  %res5 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res4, <8 x i8> %t5, 5
+  %res6 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res5, <8 x i8> %t6, 6
   ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res6
 }
 
-define {<2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>} @vector_deinterleave_load_factor8(ptr %ptr) {
+define { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @vector_deinterleave_load_factor8(ptr %p) {
 ; CHECK-LABEL: vector_deinterleave_load_factor8:
 ; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, ta, ma
+; CHECK-NEXT:    vlseg8e8.v v8, (a0)
+; CHECK-NEXT:    vmv1r.v v15, v14
+; CHECK-NEXT:    ret
+  %vec = load <64 x i8>, ptr %p
+  %d0 = call { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } @llvm.vector.deinterleave8(<64 x i8> %vec)
+  %t0 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 0
+  %t1 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 1
+  %t2 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 2
+  %t3 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 3
+  %t4 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 4
+  %t5 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 5
+  %t6 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 6
+  %t7 = extractvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %d0, 7
+  %res0 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } poison, <8 x i8> %t0, 0
+  %res1 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res0, <8 x i8> %t1, 1
+  %res2 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res1, <8 x i8> %t2, 2
+  %res3 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res2, <8 x i8> %t3, 3
+  %res4 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res3, <8 x i8> %t4, 4
+  %res5 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res4, <8 x i8> %t5, 5
+  %res6 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res5, <8 x i8> %t6, 6
+  %res7 = insertvalue { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res6, <8 x i8> %t6, 7
+  ret { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> } %res7
+}
+
+; TODO: Remove once recursive deinterleaving support is removed
+define {<2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>} @vector_deinterleave_load_factor8_recursive(ptr %ptr) {
+; CHECK-LABEL: vector_deinterleave_load_factor8_recursive:
+; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetivli zero, 2, e32, mf2, ta, ma
 ; CHECK-NEXT:    vlseg8e32.v v8, (a0)
 ; CHECK-NEXT:    ret
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleave-store.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleave-store.ll
index 8244db4..c394e7a 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleave-store.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-interleave-store.ll
@@ -198,6 +198,18 @@
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
 ; CHECK-NEXT:    vsseg4e32.v v8, (a0)
 ; CHECK-NEXT:    ret
+  %v = call <16 x i32> @llvm.vector.interleave4(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d)
+  store <16 x i32> %v, ptr %p
+  ret void
+}
+
+; TODO: Remove once recursive interleaving support is removed
+define void @vector_interleave_store_factor4_recursive(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, ptr %p) {
+; CHECK-LABEL: vector_interleave_store_factor4_recursive:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vsseg4e32.v v8, (a0)
+; CHECK-NEXT:    ret
   %v0 = call <8 x i32> @llvm.vector.interleave2.v8i32(<4 x i32> %a, <4 x i32> %c)
   %v1 = call <8 x i32> @llvm.vector.interleave2.v8i32(<4 x i32> %b, <4 x i32> %d)
   %v2 = call <16 x i32> @llvm.vector.interleave2.v16i32(<8 x i32> %v0, <8 x i32> %v1)
@@ -216,6 +228,17 @@
   ret void
 }
 
+define void @vector_interleave_store_factor6(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, <4 x i32> %e, <4 x i32> %f, ptr %p) {
+; CHECK-LABEL: vector_interleave_store_factor6:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vsseg6e32.v v8, (a0)
+; CHECK-NEXT:    ret
+  %v = call <24 x i32> @llvm.vector.interleave6(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, <4 x i32> %e, <4 x i32> %f)
+  store <24 x i32> %v, ptr %p
+  ret void
+}
+
 define void @vector_interleave_store_factor7(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, <4 x i32> %e, <4 x i32> %f, <4 x i32> %g, ptr %p) {
 ; CHECK-LABEL: vector_interleave_store_factor7:
 ; CHECK:       # %bb.0:
@@ -233,6 +256,18 @@
 ; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
 ; CHECK-NEXT:    vsseg8e32.v v8, (a0)
 ; CHECK-NEXT:    ret
+  %v = call <32 x i32> @llvm.vector.interleave8(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, <4 x i32> %e, <4 x i32> %f, <4 x i32> %g, <4 x i32> %h)
+  store <32 x i32> %v, ptr %p
+  ret void
+}
+
+; TODO: Remove once recursive interleaving support is removed
+define void @vector_interleave_store_factor8_recursive(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i32> %d, <4 x i32> %e, <4 x i32> %f, <4 x i32> %g, <4 x i32> %h, ptr %p) {
+; CHECK-LABEL: vector_interleave_store_factor8_recursive:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
+; CHECK-NEXT:    vsseg8e32.v v8, (a0)
+; CHECK-NEXT:    ret
   %v0 = call <8 x i32> @llvm.vector.interleave2.v8i32(<4 x i32> %a, <4 x i32> %e)
   %v1 = call <8 x i32> @llvm.vector.interleave2.v8i32(<4 x i32> %c, <4 x i32> %g)
   %v2 = call <16 x i32> @llvm.vector.interleave2.v16i32(<8 x i32> %v0, <8 x i32> %v1)
diff --git a/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-load.ll b/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-load.ll
index 0483bbb..9344c52 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-load.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vector-deinterleave-load.ll
@@ -368,6 +368,26 @@
 ; CHECK-NEXT:    vlseg4e8.v v8, (a0)
 ; CHECK-NEXT:    ret
   %vec = load <vscale x 32 x i8>, ptr %p
+  %d0 = call { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @llvm.vector.deinterleave4(<vscale x 32 x i8> %vec)
+  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 0
+  %t1 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 1
+  %t2 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 2
+  %t3 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 3
+  %res0 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } poison, <vscale x 8 x i8> %t0, 0
+  %res1 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res0, <vscale x 8 x i8> %t1, 1
+  %res2 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1, <vscale x 8 x i8> %t2, 2
+  %res3 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res2, <vscale x 8 x i8> %t3, 3
+  ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3
+}
+
+; TODO: Remove once recursive deinterleaving support is removed
+define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor4_recursive(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_factor4_recursive:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
+; CHECK-NEXT:    vlseg4e8.v v8, (a0)
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 32 x i8>, ptr %p
   %d0 = call {<vscale x 16 x i8>, <vscale x 16 x i8>} @llvm.vector.deinterleave2.nxv32i8(<vscale x 32 x i8> %vec)
   %d0.0 = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } %d0, 0
   %d0.1 = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } %d0, 1
@@ -406,6 +426,29 @@
   ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res4
 }
 
+define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor6(ptr %p) {
+; CHECK-LABEL: vector_deinterleave_load_factor6:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
+; CHECK-NEXT:    vlseg6e8.v v8, (a0)
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 48 x i8>, ptr %p
+  %d0 = call { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @llvm.vector.deinterleave6(<vscale x 48 x i8> %vec)
+  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 0
+  %t1 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 1
+  %t2 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 2
+  %t3 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 3
+  %t4 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 4
+  %t5 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 5
+  %res0 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } poison, <vscale x 8 x i8> %t0, 0
+  %res1 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res0, <vscale x 8 x i8> %t1, 1
+  %res2 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1, <vscale x 8 x i8> %t2, 2
+  %res3 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res2, <vscale x 8 x i8> %t3, 3
+  %res4 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3, <vscale x 8 x i8> %t4, 4
+  %res5 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res4, <vscale x 8 x i8> %t5, 5
+  ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res5
+}
+
 define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor7(ptr %p) {
 ; CHECK-LABEL: vector_deinterleave_load_factor7:
 ; CHECK:       # %bb.0:
@@ -426,14 +469,42 @@
   %res2 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1, <vscale x 8 x i8> %t2, 2
   %res3 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res2, <vscale x 8 x i8> %t3, 3
   %res4 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3, <vscale x 8 x i8> %t4, 4
-  %res5 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3, <vscale x 8 x i8> %t5, 5
-  %res6 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3, <vscale x 8 x i8> %t6, 6
+  %res5 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res4, <vscale x 8 x i8> %t5, 5
+  %res6 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res5, <vscale x 8 x i8> %t6, 6
   ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res6
 }
 
-define {<vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>} @vector_deinterleave_load_factor8(ptr %ptr) {
+define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor8(ptr %p) {
 ; CHECK-LABEL: vector_deinterleave_load_factor8:
 ; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
+; CHECK-NEXT:    vlseg8e8.v v8, (a0)
+; CHECK-NEXT:    ret
+  %vec = load <vscale x 64 x i8>, ptr %p
+  %d0 = call { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @llvm.vector.deinterleave8(<vscale x 64 x i8> %vec)
+  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 0
+  %t1 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 1
+  %t2 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 2
+  %t3 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 3
+  %t4 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 4
+  %t5 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 5
+  %t6 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 6
+  %t7 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 7
+  %res0 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } poison, <vscale x 8 x i8> %t0, 0
+  %res1 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res0, <vscale x 8 x i8> %t1, 1
+  %res2 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1, <vscale x 8 x i8> %t2, 2
+  %res3 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res2, <vscale x 8 x i8> %t3, 3
+  %res4 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3, <vscale x 8 x i8> %t4, 4
+  %res5 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res4, <vscale x 8 x i8> %t5, 5
+  %res6 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res5, <vscale x 8 x i8> %t6, 6
+  %res7 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res6, <vscale x 8 x i8> %t7, 7
+  ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res7
+}
+
+; TODO: Remove once recursive deinterleaving support is removed
+define {<vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>} @vector_deinterleave_load_factor8_recursive(ptr %ptr) {
+; CHECK-LABEL: vector_deinterleave_load_factor8_recursive:
+; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a1, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vlseg8e32.v v8, (a0)
 ; CHECK-NEXT:    ret
diff --git a/llvm/test/CodeGen/RISCV/rvv/vector-interleave-store.ll b/llvm/test/CodeGen/RISCV/rvv/vector-interleave-store.ll
index 4332ca4..3751967 100644
--- a/llvm/test/CodeGen/RISCV/rvv/vector-interleave-store.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vector-interleave-store.ll
@@ -250,9 +250,21 @@
   ret void
 }
 
-define void @vector_interleave_store_factor4(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c, <vscale x 4 x i32> %d, ptr %p) {
+define void @vector_interleave_store_factor4(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, <vscale x 2 x i32> %c, <vscale x 2 x i32> %d, ptr %p) {
 ; CHECK-LABEL: vector_interleave_store_factor4:
 ; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vsseg4e32.v v8, (a0)
+; CHECK-NEXT:    ret
+  %v = call <vscale x 8 x i32> @llvm.vector.interleave4(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, <vscale x 2 x i32> %c, <vscale x 2 x i32> %d)
+  store <vscale x 8 x i32> %v, ptr %p
+  ret void
+}
+
+; TODO: Remove once recursive interleaving support is removed
+define void @vector_interleave_store_factor4_recursive(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c, <vscale x 4 x i32> %d, ptr %p) {
+; CHECK-LABEL: vector_interleave_store_factor4_recursive:
+; CHECK:       # %bb.0:
 ; CHECK-NEXT:    vsetvli a1, zero, e32, m2, ta, ma
 ; CHECK-NEXT:    vsseg4e32.v v8, (a0)
 ; CHECK-NEXT:    ret
@@ -274,6 +286,17 @@
   ret void
 }
 
+define void @vector_interleave_store_factor6(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, <vscale x 2 x i32> %c, <vscale x 2 x i32> %d, <vscale x 2 x i32> %e, <vscale x 2 x i32> %f, ptr %p) {
+; CHECK-LABEL: vector_interleave_store_factor6:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vsseg6e32.v v8, (a0)
+; CHECK-NEXT:    ret
+  %v = call <vscale x 12 x i32> @llvm.vector.interleave6(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, <vscale x 2 x i32> %c, <vscale x 2 x i32> %d, <vscale x 2 x i32> %e, <vscale x 2 x i32> %f)
+  store <vscale x 12 x i32> %v, ptr %p
+  ret void
+}
+
 define void @vector_interleave_store_factor7(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, <vscale x 2 x i32> %c, <vscale x 2 x i32> %d, <vscale x 2 x i32> %e, <vscale x 2 x i32> %f, <vscale x 2 x i32> %g, ptr %p) {
 ; CHECK-LABEL: vector_interleave_store_factor7:
 ; CHECK:       # %bb.0:
@@ -291,6 +314,18 @@
 ; CHECK-NEXT:    vsetvli a1, zero, e32, m1, ta, ma
 ; CHECK-NEXT:    vsseg8e32.v v8, (a0)
 ; CHECK-NEXT:    ret
+  %v = call <vscale x 16 x i32> @llvm.vector.interleave8(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, <vscale x 2 x i32> %c, <vscale x 2 x i32> %d, <vscale x 2 x i32> %e, <vscale x 2 x i32> %f, <vscale x 2 x i32> %g, <vscale x 2 x i32> %h)
+  store <vscale x 16 x i32> %v, ptr %p
+  ret void
+}
+
+; TODO: Remove once recursive interleaving support is removed
+define void @vector_interleave_store_factor8_recursive(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, <vscale x 2 x i32> %c, <vscale x 2 x i32> %d, <vscale x 2 x i32> %e, <vscale x 2 x i32> %f, <vscale x 2 x i32> %g, <vscale x 2 x i32> %h, ptr %p) {
+; CHECK-LABEL: vector_interleave_store_factor8_recursive:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a1, zero, e32, m1, ta, ma
+; CHECK-NEXT:    vsseg8e32.v v8, (a0)
+; CHECK-NEXT:    ret
   %v0 = call <vscale x 4 x i32> @llvm.vector.interleave2.nxv4i32(<vscale x 2 x i32> %a, <vscale x 2 x i32> %e)
   %v1 = call <vscale x 4 x i32> @llvm.vector.interleave2.nxv4i32(<vscale x 2 x i32> %c, <vscale x 2 x i32> %g)
   %v2 = call <vscale x 8 x i32> @llvm.vector.interleave2.nxv8i32(<vscale x 4 x i32> %v0, <vscale x 4 x i32> %v1)
diff --git a/llvm/test/Transforms/InterleavedAccess/RISCV/interleaved-accesses.ll b/llvm/test/Transforms/InterleavedAccess/RISCV/interleaved-accesses.ll
index 0a20e03..87b16d1 100644
--- a/llvm/test/Transforms/InterleavedAccess/RISCV/interleaved-accesses.ll
+++ b/llvm/test/Transforms/InterleavedAccess/RISCV/interleaved-accesses.ll
@@ -167,6 +167,49 @@
 ; RV64-NEXT:    ret void
 ;
   %interleaved.vec = load <vscale x 16 x i32>, ptr %ptr
+  %v = call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave4.nxv16i32(<vscale x 16 x i32> %interleaved.vec)
+  %t0 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } %v, 0
+  %t1 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } %v, 1
+  %t2 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } %v, 2
+  %t3 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } %v, 3
+  ret void
+}
+
+; TODO: Remove once recursive deinterleaving support is removed
+define void @load_factor4_vscale_recursive(ptr %ptr) {
+; RV32-LABEL: @load_factor4_vscale_recursive(
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 16 x i8>, 4) @llvm.riscv.vlseg4.triscv.vector.tuple_nxv16i8_4t.p0.i32(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
+; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 0)
+; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } poison, <vscale x 4 x i32> [[TMP2]], 0
+; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 1)
+; RV32-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP3]], <vscale x 4 x i32> [[TMP4]], 1
+; RV32-NEXT:    [[TMP6:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 2)
+; RV32-NEXT:    [[TMP7:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP5]], <vscale x 4 x i32> [[TMP6]], 2
+; RV32-NEXT:    [[TMP8:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 3)
+; RV32-NEXT:    [[TMP9:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP7]], <vscale x 4 x i32> [[TMP8]], 3
+; RV32-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 0
+; RV32-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 1
+; RV32-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 2
+; RV32-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 3
+; RV32-NEXT:    ret void
+;
+; RV64-LABEL: @load_factor4_vscale_recursive(
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 16 x i8>, 4) @llvm.riscv.vlseg4.triscv.vector.tuple_nxv16i8_4t.p0.i64(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
+; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 0)
+; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } poison, <vscale x 4 x i32> [[TMP2]], 0
+; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 1)
+; RV64-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP3]], <vscale x 4 x i32> [[TMP4]], 1
+; RV64-NEXT:    [[TMP6:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 2)
+; RV64-NEXT:    [[TMP7:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP5]], <vscale x 4 x i32> [[TMP6]], 2
+; RV64-NEXT:    [[TMP8:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 3)
+; RV64-NEXT:    [[TMP9:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP7]], <vscale x 4 x i32> [[TMP8]], 3
+; RV64-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 0
+; RV64-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 1
+; RV64-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 2
+; RV64-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[TMP9]], 3
+; RV64-NEXT:    ret void
+;
+  %interleaved.vec = load <vscale x 16 x i32>, ptr %ptr
   %d0 = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> %interleaved.vec)
   %d0.0 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %d0, 0
   %d0.1 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %d0, 1
@@ -287,6 +330,62 @@
   ret void
 }
 
+define void @load_factor6_vscale(ptr %ptr) {
+; RV32-LABEL: @load_factor6_vscale(
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.vlseg6.triscv.vector.tuple_nxv8i8_6t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
+; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 0)
+; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
+; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 1)
+; RV32-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP3]], <vscale x 2 x i32> [[TMP4]], 1
+; RV32-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 2)
+; RV32-NEXT:    [[TMP7:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP5]], <vscale x 2 x i32> [[TMP6]], 2
+; RV32-NEXT:    [[TMP8:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 3)
+; RV32-NEXT:    [[TMP9:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP7]], <vscale x 2 x i32> [[TMP8]], 3
+; RV32-NEXT:    [[TMP10:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 4)
+; RV32-NEXT:    [[TMP11:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP9]], <vscale x 2 x i32> [[TMP10]], 4
+; RV32-NEXT:    [[TMP12:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 5)
+; RV32-NEXT:    [[TMP13:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP11]], <vscale x 2 x i32> [[TMP12]], 5
+; RV32-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 0
+; RV32-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 1
+; RV32-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 2
+; RV32-NEXT:    [[TMP17:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 3
+; RV32-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 4
+; RV32-NEXT:    [[TMP19:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 5
+; RV32-NEXT:    ret void
+;
+; RV64-LABEL: @load_factor6_vscale(
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.vlseg6.triscv.vector.tuple_nxv8i8_6t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
+; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 0)
+; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
+; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 1)
+; RV64-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP3]], <vscale x 2 x i32> [[TMP4]], 1
+; RV64-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 2)
+; RV64-NEXT:    [[TMP7:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP5]], <vscale x 2 x i32> [[TMP6]], 2
+; RV64-NEXT:    [[TMP8:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 3)
+; RV64-NEXT:    [[TMP9:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP7]], <vscale x 2 x i32> [[TMP8]], 3
+; RV64-NEXT:    [[TMP10:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 4)
+; RV64-NEXT:    [[TMP11:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP9]], <vscale x 2 x i32> [[TMP10]], 4
+; RV64-NEXT:    [[TMP12:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 5)
+; RV64-NEXT:    [[TMP13:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP11]], <vscale x 2 x i32> [[TMP12]], 5
+; RV64-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 0
+; RV64-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 1
+; RV64-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 2
+; RV64-NEXT:    [[TMP17:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 3
+; RV64-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 4
+; RV64-NEXT:    [[TMP19:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], 5
+; RV64-NEXT:    ret void
+;
+  %interleaved.vec = load <vscale x 12 x i32>, ptr %ptr
+  %v = call {  <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } @llvm.vector.deinterleave6.nxv12i32(<vscale x 12 x i32> %interleaved.vec)
+  %t0 = extractvalue {  <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 0
+  %t1 = extractvalue {  <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 1
+  %t2 = extractvalue {  <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 2
+  %t3 = extractvalue {  <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 3
+  %t4 = extractvalue {  <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 4
+  %t5 = extractvalue {  <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 5
+  ret void
+}
+
 define void @load_factor7(ptr %ptr) {
 ; RV32-LABEL: @load_factor7(
 ; RV32-NEXT:    [[TMP1:%.*]] = call { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> } @llvm.riscv.seg7.load.mask.v4i32.p0.i32(ptr [[PTR:%.*]], <4 x i1> splat (i1 true), i32 4)
@@ -479,6 +578,77 @@
 ; RV64-NEXT:    ret void
 ;
   %interleaved.vec = load <vscale x 16 x i32>, ptr %ptr
+  %v = call { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } @llvm.vector.deinterleave8.nxv16i32(<vscale x 16 x i32> %interleaved.vec)
+  %t0 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 0
+  %t1 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 1
+  %t2 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 2
+  %t3 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 3
+  %t4 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 4
+  %t5 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 5
+  %t6 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 6
+  %t7 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %v, 7
+  ret void
+}
+
+; TODO: Remove once recursive deinterleaving support is removed
+define void @load_factor8_vscale_recursive(ptr %ptr) {
+; RV32-LABEL: @load_factor8_vscale_recursive(
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.vlseg8.triscv.vector.tuple_nxv8i8_8t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
+; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 0)
+; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
+; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 1)
+; RV32-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP3]], <vscale x 2 x i32> [[TMP4]], 1
+; RV32-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 2)
+; RV32-NEXT:    [[TMP7:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP5]], <vscale x 2 x i32> [[TMP6]], 2
+; RV32-NEXT:    [[TMP8:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 3)
+; RV32-NEXT:    [[TMP9:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP7]], <vscale x 2 x i32> [[TMP8]], 3
+; RV32-NEXT:    [[TMP10:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 4)
+; RV32-NEXT:    [[TMP11:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP9]], <vscale x 2 x i32> [[TMP10]], 4
+; RV32-NEXT:    [[TMP12:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 5)
+; RV32-NEXT:    [[TMP13:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP11]], <vscale x 2 x i32> [[TMP12]], 5
+; RV32-NEXT:    [[TMP14:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 6)
+; RV32-NEXT:    [[TMP15:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], <vscale x 2 x i32> [[TMP14]], 6
+; RV32-NEXT:    [[TMP16:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 7)
+; RV32-NEXT:    [[TMP17:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP15]], <vscale x 2 x i32> [[TMP16]], 7
+; RV32-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 0
+; RV32-NEXT:    [[TMP19:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 1
+; RV32-NEXT:    [[TMP20:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 2
+; RV32-NEXT:    [[TMP21:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 3
+; RV32-NEXT:    [[TMP22:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 4
+; RV32-NEXT:    [[TMP23:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 5
+; RV32-NEXT:    [[TMP24:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 6
+; RV32-NEXT:    [[TMP25:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 7
+; RV32-NEXT:    ret void
+;
+; RV64-LABEL: @load_factor8_vscale_recursive(
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.vlseg8.triscv.vector.tuple_nxv8i8_8t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
+; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 0)
+; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
+; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 1)
+; RV64-NEXT:    [[TMP5:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP3]], <vscale x 2 x i32> [[TMP4]], 1
+; RV64-NEXT:    [[TMP6:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 2)
+; RV64-NEXT:    [[TMP7:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP5]], <vscale x 2 x i32> [[TMP6]], 2
+; RV64-NEXT:    [[TMP8:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 3)
+; RV64-NEXT:    [[TMP9:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP7]], <vscale x 2 x i32> [[TMP8]], 3
+; RV64-NEXT:    [[TMP10:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 4)
+; RV64-NEXT:    [[TMP11:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP9]], <vscale x 2 x i32> [[TMP10]], 4
+; RV64-NEXT:    [[TMP12:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 5)
+; RV64-NEXT:    [[TMP13:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP11]], <vscale x 2 x i32> [[TMP12]], 5
+; RV64-NEXT:    [[TMP14:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 6)
+; RV64-NEXT:    [[TMP15:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP13]], <vscale x 2 x i32> [[TMP14]], 6
+; RV64-NEXT:    [[TMP16:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 7)
+; RV64-NEXT:    [[TMP17:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP15]], <vscale x 2 x i32> [[TMP16]], 7
+; RV64-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 0
+; RV64-NEXT:    [[TMP19:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 1
+; RV64-NEXT:    [[TMP20:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 2
+; RV64-NEXT:    [[TMP21:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 3
+; RV64-NEXT:    [[TMP22:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 4
+; RV64-NEXT:    [[TMP23:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 5
+; RV64-NEXT:    [[TMP24:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 6
+; RV64-NEXT:    [[TMP25:%.*]] = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } [[TMP17]], 7
+; RV64-NEXT:    ret void
+;
+  %interleaved.vec = load <vscale x 16 x i32>, ptr %ptr
   %d0 = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> %interleaved.vec)
   %d0.0 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %d0, 0
   %d0.1 = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } %d0, 1
@@ -616,16 +786,39 @@
   ret void
 }
 
-define void @store_factor4_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1) {
+define void @store_factor4_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3) {
 ; RV32-LABEL: @store_factor4_vscale(
 ; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
+; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
+; RV32-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
+; RV32-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
+; RV32-NEXT:    call void @llvm.riscv.vsseg4.triscv.vector.tuple_nxv8i8_4t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP4]], ptr [[PTR:%.*]], i32 -1, i32 3)
+; RV32-NEXT:    ret void
+;
+; RV64-LABEL: @store_factor4_vscale(
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
+; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
+; RV64-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
+; RV64-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
+; RV64-NEXT:    call void @llvm.riscv.vsseg4.triscv.vector.tuple_nxv8i8_4t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP4]], ptr [[PTR:%.*]], i64 -1, i64 3)
+; RV64-NEXT:    ret void
+;
+  %interleaved.vec = call <vscale x 32 x i8> @llvm.vector.interleave4.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3)
+  store <vscale x 32 x i8> %interleaved.vec, ptr %ptr
+  ret void
+}
+
+; TODO: Remove once recursive interleaving support is removed
+define void @store_factor4_vscale_recursive(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1) {
+; RV32-LABEL: @store_factor4_vscale_recursive(
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
 ; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP1]], <vscale x 8 x i8> [[V0]], i32 1)
 ; RV32-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP2]], <vscale x 8 x i8> [[V1:%.*]], i32 2)
 ; RV32-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP3]], <vscale x 8 x i8> [[V1]], i32 3)
 ; RV32-NEXT:    call void @llvm.riscv.vsseg4.triscv.vector.tuple_nxv8i8_4t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP4]], ptr [[PTR:%.*]], i32 -1, i32 3)
 ; RV32-NEXT:    ret void
 ;
-; RV64-LABEL: @store_factor4_vscale(
+; RV64-LABEL: @store_factor4_vscale_recursive(
 ; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
 ; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP1]], <vscale x 8 x i8> [[V0]], i32 1)
 ; RV64-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP2]], <vscale x 8 x i8> [[V1:%.*]], i32 2)
@@ -736,6 +929,32 @@
   ret void
 }
 
+define void @store_factor6_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3, <vscale x 8 x i8> %v4, <vscale x 8 x i8> %v5) {
+; RV32-LABEL: @store_factor6_vscale(
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
+; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
+; RV32-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
+; RV32-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
+; RV32-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP4]], <vscale x 8 x i8> [[V4:%.*]], i32 4)
+; RV32-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP5]], <vscale x 8 x i8> [[V5:%.*]], i32 5)
+; RV32-NEXT:    call void @llvm.riscv.vsseg6.triscv.vector.tuple_nxv8i8_6t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP6]], ptr [[PTR:%.*]], i32 -1, i32 3)
+; RV32-NEXT:    ret void
+;
+; RV64-LABEL: @store_factor6_vscale(
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
+; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
+; RV64-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
+; RV64-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
+; RV64-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP4]], <vscale x 8 x i8> [[V4:%.*]], i32 4)
+; RV64-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP5]], <vscale x 8 x i8> [[V5:%.*]], i32 5)
+; RV64-NEXT:    call void @llvm.riscv.vsseg6.triscv.vector.tuple_nxv8i8_6t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP6]], ptr [[PTR:%.*]], i64 -1, i64 3)
+; RV64-NEXT:    ret void
+;
+  %interleaved.vec = call <vscale x 48 x i8> @llvm.vector.interleave6.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3, <vscale x 8 x i8> %v4, <vscale x 8 x i8> %v5)
+  store <vscale x 48 x i8> %interleaved.vec, ptr %ptr
+  ret void
+}
+
 define void @store_factor7_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3, <vscale x 8 x i8> %v4, <vscale x 8 x i8> %v5, <vscale x 8 x i8> %v6) {
 ; RV32-LABEL: @store_factor7_vscale(
 ; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_7t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
@@ -764,9 +983,40 @@
   ret void
 }
 
-define void @store_factor8_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3) {
+define void @store_factor8_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3, <vscale x 8 x i8> %v4, <vscale x 8 x i8> %v5, <vscale x 8 x i8> %v6, <vscale x 8 x i8> %v7) {
 ; RV32-LABEL: @store_factor8_vscale(
 ; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
+; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
+; RV32-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
+; RV32-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
+; RV32-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP4]], <vscale x 8 x i8> [[V4:%.*]], i32 4)
+; RV32-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP5]], <vscale x 8 x i8> [[V5:%.*]], i32 5)
+; RV32-NEXT:    [[TMP7:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP6]], <vscale x 8 x i8> [[V6:%.*]], i32 6)
+; RV32-NEXT:    [[TMP8:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP7]], <vscale x 8 x i8> [[V7:%.*]], i32 7)
+; RV32-NEXT:    call void @llvm.riscv.vsseg8.triscv.vector.tuple_nxv8i8_8t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP8]], ptr [[PTR:%.*]], i32 -1, i32 3)
+; RV32-NEXT:    ret void
+;
+; RV64-LABEL: @store_factor8_vscale(
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
+; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
+; RV64-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
+; RV64-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
+; RV64-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP4]], <vscale x 8 x i8> [[V4:%.*]], i32 4)
+; RV64-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP5]], <vscale x 8 x i8> [[V5:%.*]], i32 5)
+; RV64-NEXT:    [[TMP7:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP6]], <vscale x 8 x i8> [[V6:%.*]], i32 6)
+; RV64-NEXT:    [[TMP8:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP7]], <vscale x 8 x i8> [[V7:%.*]], i32 7)
+; RV64-NEXT:    call void @llvm.riscv.vsseg8.triscv.vector.tuple_nxv8i8_8t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP8]], ptr [[PTR:%.*]], i64 -1, i64 3)
+; RV64-NEXT:    ret void
+;
+  %interleaved.vec = call <vscale x 64 x i8> @llvm.vector.interleave8.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3, <vscale x 8 x i8> %v4, <vscale x 8 x i8> %v5, <vscale x 8 x i8> %v6, <vscale x 8 x i8> %v7)
+  store <vscale x 64 x i8> %interleaved.vec, ptr %ptr
+  ret void
+}
+
+; TODO: Remove once recursive interleaving support is removed
+define void @store_factor8_vscale_recursive(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3) {
+; RV32-LABEL: @store_factor8_vscale_recursive(
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
 ; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], <vscale x 8 x i8> [[V2:%.*]], i32 1)
 ; RV32-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP2]], <vscale x 8 x i8> [[V0]], i32 2)
 ; RV32-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP3]], <vscale x 8 x i8> [[V2]], i32 3)
@@ -777,7 +1027,7 @@
 ; RV32-NEXT:    call void @llvm.riscv.vsseg8.triscv.vector.tuple_nxv8i8_8t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP8]], ptr [[PTR:%.*]], i32 -1, i32 3)
 ; RV32-NEXT:    ret void
 ;
-; RV64-LABEL: @store_factor8_vscale(
+; RV64-LABEL: @store_factor8_vscale_recursive(
 ; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
 ; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], <vscale x 8 x i8> [[V2:%.*]], i32 1)
 ; RV64-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP2]], <vscale x 8 x i8> [[V0]], i32 2)